Synthesis-Guided Feature Learning for Cross-Spectral Periocular Recognition

TL;DR

This paper introduces a novel cross-spectral periocular recognition method using a coupled GAN that learns a shared feature space and reconstructs intra-spectral images, significantly outperforming current state-of-the-art techniques.

Contribution

The paper proposes a Coupled Conditional GAN with paired U-Nets for improved cross-spectral periocular recognition, incorporating intra-spectral reconstruction for better domain-invariant features.

Findings

Achieved 98.65% AUC and 5.14% EER on Hong Kong PolyU dataset.

Achieved 99.31% AUC and 3.99% EER on Cross-Eyed dataset.

Outperformed current state-of-the-art methods in cross-spectral recognition.

Abstract

A common yet challenging scenario in periocular biometrics is cross-spectral matching - in particular, the matching of visible wavelength against near-infrared (NIR) periocular images. We propose a novel approach to cross-spectral periocular verification that primarily focuses on learning a mapping from visible and NIR periocular images to a shared latent representational subspace, and supports this effort by simultaneously learning intra-spectral image reconstruction. We show the auxiliary image reconstruction task (and in particular the reconstruction of high-level, semantic features) results in learning a more discriminative, domain-invariant subspace compared to the baseline while incurring no additional computational or memory costs at test-time. The proposed Coupled Conditional Generative Adversarial Network (CoGAN) architecture uses paired generator networks (one operating on visible images and the other on NIR) composed of U-Nets with ResNet-18 encoders trained for feature learning via contrastive loss and for intra-spectral image reconstruction with adversarial, pixel-based, and perceptual reconstruction losses. Moreover, the proposed CoGAN model beats the current state-of-art (SotA) in cross-spectral periocular recognition. On the Hong Kong PolyU benchmark dataset, we achieve 98.65% AUC and 5.14% EER compared to the SotA EER of 8.02%. On the Cross-Eyed dataset, we achieve 99.31% AUC and 3.99% EER versus SotA EER of 4.39%.